SPS Webinar: Performance Analysis of Differential Privacy for Personalized Federated Learning
Date: 12 March 2025
Time: 9:00 AM ET (New York Time)
Presenter(s): Dr. Ming Ding
Based on the IEEE Xplore® article:
Personalized Federated Learning with Differential Privacy and Convergence Guarantee, published in the IEEE Transactions on Information Forensics and Security, July 2023.
Download article: Original article will be made publicly available for download on the day of the webinar for 48 hours.
Abstract
This webinar session will explore personalized federated learning (PFL), a cutting-edge method that creates customized models for diverse client needs, enhancing model convergence through meta-learning. The presenter will address the significant challenges associated with information leakage and unveil a differential privacy (DP) based PFL framework. His approach designs a privacy budget allocation scheme rooted in the Rényi Differential Privacy composition theory. Throughout the session, he will discuss the formulation of convergence bounds applicable to both convex and non-convex loss functions. This analysis leads to optimal strategies for determining the most effective model size and achieving the best balance among communication rounds, convergence performance, and privacy considerations. Supported by thorough evaluations on various real-life datasets, their findings corroborate their theoretical predictions and serve as a practical guide for developing DP-PFL algorithms. This webinar is perfect for researchers, data scientists, and practitioners eager to deepen their knowledge and enhance the privacy and efficiency of their federated learning projects. Join us to gain valuable insights into how to design PFL systems and ensure robust privacy protections while maintaining high performance.
Biography
Ming Ding (M’12-SM’17) received the B.S. (with first-class Hons.) and M.S. degrees in electronics engineering and the Ph.D. degree in signal and information processing from Shanghai Jiao Tong University (SJTU) Shanghai, China, in 2004, 2007 & 2011 respectively.
He is currently a Principal Research Scientist and Science Lead at Data61, CSIRO, in Sydney, NSW, Australia. He is also an Adjunct Professor at Swinburne University of Technology, Australia. From April 2007 to September 2014, he worked at Sharp Laboratories of China as a Researcher/Senior Researcher/Principal Researcher. His research interests include data privacy and security, machine learning and AI, and information technology.
Dr. Ding has co-authored more than 250 papers in IEEE/ACM journals and conferences, all in recognized venues, and around 20 3GPP standardization contributions, as well as two books, i.e., “Multi-point Cooperative Communication Systems: Theory and Applications” (Springer, 2013) and “Fundamentals of Ultra-Dense Wireless Networks” (Cambridge University Press, 2022). He also holds 21 US patents and has co-invented another 100+ patents on 4G/5G technologies. Currently, he is an editor of IEEE Communications Surveys and Tutorials. Additionally, he has served as a guest editor/co-chair/co-tutor/TPC member for multiple IEEE top-tier journals/conferences and received several awards for his research work and professional services, including the prestigious IEEE Signal Processing Society Best Paper Award in 2022 and Highly Cited Researcher recognized by Clarivate Analytics in 2024.
